apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
doc-to-lora/scripts/short_ctx
History
ShinnosukeUesakaSakana d99fa8732b
Add distillation training (#5) 
- work with vllm self-gen data (everything is tokenized during self-gen)
- fix chat template!
- not use liger kernel for distillation (for both training and eval)
2025-07-29 15:32:06 +09:00
..
gemma_fw_qa_level_0.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_fw_qa_level_0_tiny.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_fw_qa_level_1.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_fw_qa_level_2.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_fw_qa_level_3.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_fw_qa_level_3_tiny.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_qa_short_ctx.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_exp_default.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_exp_default_max_qas_per_sample_1.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_exp_default_more_prehead.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_exp_default_more_prehead_max_qas_per_sample_1.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_exp_self_attn.sh Perceiver blocks + layer-to-layer (#4) 2025-07-07 17:31:07 +09:00
gemma_qa_short_ctx_no_fw_qa.sh eval generative only + scripts 2025-06-30 16:41:26 +09:00
gemma_qa_short_ctx_old_conf.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_old_conf_8_gpus.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_old_conf_distill.sh Add distillation training (#5) 2025-07-29 15:32:06 +09:00
gemma_qa_short_ctx_old_conf_more_grad_acc.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_l2l.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_l2l_32_max_qas_len.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_l2l_64_max_qas_len.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_l2l_128_max_qas_len.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_l2l_512_max_qas_len.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_l2l_max_qas_per_sample_1.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_perceiver_max_qas_per_sample_1.sh short ctx exp scripts 2025-07-21 09:05:08 +00:00
gemma_qa_short_ctx_self_gen.sh eval generative only + scripts 2025-06-30 16:41:26 +09:00
gemma_qa_short_ctx_self_gen_no_fw_qa.sh eval generative only + scripts 2025-06-30 16:41:26 +09:00
gemma_squad.sh qa data exp 2025-06-26 15:30:26 +09:00
gemma_squad_and_fw_qa_level_3.sh qa data exp 2025-06-26 15:30:26 +09:00